Paper Info
Title
Kinect analysis: a system for recording, analysing and sharing multimodal interaction elicitation studies
Abstract
Recently, guessability studies have become a popular means among researchers to elicit user-defined interaction sets involving gesture, speech and multimodal input. However, tool support for capturing and analysing interaction proposals is lacking and the method itself is still evolving. This paper presents Kinect Analysis---a system designed for interaction elicitation studies with support for record-and-replay, visualisation and analysis based on Kinect's depth, audio and video streams. Kinect Analysis enables post-hoc analysis during playback and live analysis with real-time feedback while recording. In particular, new visualisations such as skeletal joint traces and heatmaps can be superimposed for analysis and comparison of multiple recordings. It also introduces KinectScript---a simple scripting language to query recordings and automate analysis tasks based on skeleton, distance, audio and gesture scripts. The paper discusses Kinect Analysis both as a tool and a method that could enable researchers to more easily collect, study and share interaction proposals. Using data from a previous guessability study with 25 users, we show that Kinect Analysis in combination with KinectScript is useful and effective for a range of analysis tasks.
Year
DOI
Venue
2015
10.1145/2774225.2774846
international conference devoted to engineering usable and effective interactive computing systems
Field
DocType
Citations 
Multimodal interaction,Gesture,Computer science,Visualization,Human–computer interaction,Multimedia,Scripting language
Conference
7
PageRank 
References 
Authors
0.54
27
3
Name
Order
Citations
PageRank
Michael Nebeling135629.81
David Ott2140.99
Moira C. Norrie31317201.70